{
  "docId": "019dd923-5e88-73ef-bd5d-0856e1444fb9",
  "docSlug": "8757f1b44ef7f176",
  "documentTitle": "2024 Air Street Capital The State of AI Report 2024",
  "authorId": "AirStreetCapital",
  "authorName": "Air Street Capital",
  "documentKindSlug": "consulting-deck",
  "documentKindLabel": "Consulting deck",
  "sourceTypeSlug": "vc_research",
  "sourceTypeLabel": "VC research",
  "presentationDate": null,
  "orientation": "landscape",
  "aspectRatio": 1.777,
  "pageNumber": 15,
  "pageCount": 213,
  "prevPage": 14,
  "nextPage": 16,
  "slideType": "case_study",
  "function": "illustrate_case",
  "density": "dense",
  "nDataPoints": 20,
  "notes": "Includes a Chatbot Arena chart and a screenshot of a viral YouTube video demonstrating o1's coding capabilities.",
  "elementsJson": [
    "headline_text",
    "paragraph",
    "scatter_plot",
    "screenshot"
  ],
  "metadataConfidence": 1,
  "imagePath": null,
  "slideHref": "/slides/019dd923-5e88-73ef-bd5d-0856e1444fb9/15",
  "deckHref": "/decks/019dd923-5e88-73ef-bd5d-0856e1444fb9",
  "deckJsonHref": "/decks/019dd923-5e88-73ef-bd5d-0856e1444fb9.json",
  "deckAnchorHref": "/decks/019dd923-5e88-73ef-bd5d-0856e1444fb9#slide-15",
  "components": [
    {
      "bbox": null,
      "kind": "callout",
      "text": "The community were quick to put o1 through its paces, finding that it performed significantly better than other LLMs on certain logical problems and puzzles.",
      "attrs": null,
      "subkind": null,
      "toolName": "Visual emphasis",
      "toolSlug": "visual-emphasis",
      "confidence": null,
      "componentId": "019dd952-47c3-7407-8d0f-fbc4b92450f5",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.45,
        "w": 0.45,
        "x": 0.02,
        "y": 0.48
      },
      "kind": "chart",
      "text": "More Statistics for Chatbot Arena - Math",
      "attrs": null,
      "subkind": "bar-vertical",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "2bcb4ebe-1835-4cdd-986d-a33c50013ffd",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.45,
        "w": 0.48,
        "x": 0.49,
        "y": 0.48
      },
      "kind": "image",
      "text": "YouTube video screenshot of PhD student reacting to o1 code generation",
      "attrs": null,
      "subkind": "screenshot",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "8818d8b5-a572-4fbb-bbe7-785ad5f3dad2",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": null,
      "kind": "metric",
      "text": "Chatbot Arena Math Rating: 1360+",
      "attrs": null,
      "subkind": "primary",
      "toolName": "Quantification",
      "toolSlug": "quantification",
      "confidence": null,
      "componentId": "019dd952-47c3-7407-8d0f-ff8d7e2172c5",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.25,
        "w": 0.96,
        "x": 0.02,
        "y": 0.22
      },
      "kind": "paragraph",
      "text": "The community were quick to put o1 through its paces, finding that it performed significantly better than other LLMs on certain logical problems and puzzles. Its true edge shone through, however, on complex math and science tasks, with a viral video of a PhD student reacting with astonishment as it reproduced a year of his PhD code in approximately an hour. However, the model remains weaker on certain kinds of spatial reasoning. Like its predecessors, it can't play chess to save its life... yet.",
      "attrs": null,
      "subkind": "paragraph",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "4bf0ed4e-87be-4482-851c-b0c132b98fdf",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.03,
        "w": 0.6,
        "x": 0.02,
        "y": 0.02
      },
      "kind": "title",
      "text": "Introduction | Research | Industry | Politics | Safety | Predictions",
      "attrs": null,
      "subkind": "headline",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "5403814e-83aa-4e25-be17-dff90540a34d",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.05,
        "w": 0.75,
        "x": 0.02,
        "y": 0.14
      },
      "kind": "title",
      "text": "o1 showcases both areas of incredible strength and persistent weakness",
      "attrs": null,
      "subkind": "headline",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "e6f9481e-971d-4e58-ab8b-0a8e06632c41",
      "frameworkName": null,
      "frameworkSlug": null
    }
  ],
  "metrics": [],
  "tools": [
    {
      "name": "Antithesis",
      "slug": "antithesis",
      "agent": "Storyteller",
      "layer": "loop",
      "matchId": "019dd95a-1055-74e0-a958-603111f7ca60",
      "evidence": "Strength vs weakness juxtaposition built into title",
      "confidence": 75
    },
    {
      "name": "Action Titles",
      "slug": "action-titles",
      "agent": "Architect",
      "layer": "slide",
      "matchId": "019dd95a-1055-74e0-a958-5ed6e84dfbf6",
      "evidence": "Title 'o1 showcases both areas of incredible strength and persistent weakness'",
      "confidence": 90
    }
  ],
  "frameworks": [],
  "arcBeats": [
    {
      "to": 153,
      "from": 9,
      "beatId": "019dd95a-0682-776c-8e35-5f2398b8d1d0",
      "arcName": "The Triple Take",
      "arcSlug": "triple-take",
      "beatName": "The Facts (What)",
      "beatSlug": "triple-take-the-facts-what",
      "evidence": "Exec summary + Research + Industry sections inventory the year",
      "position": 1,
      "confidence": 78,
      "parentBeatName": "Setup",
      "parentBeatSlug": "setup"
    },
    {
      "to": 85,
      "from": 12,
      "beatId": "019dd95a-0682-776c-8e35-6d9d8ee06d0a",
      "arcName": "Voyage and Return",
      "arcSlug": "voyage-return",
      "beatName": "The Unknown",
      "beatSlug": "voyage-return-the-unknown",
      "evidence": "Research section explores frontier model uncharted territory",
      "position": 2,
      "confidence": 55,
      "parentBeatName": "Complication",
      "parentBeatSlug": "complication"
    }
  ],
  "loops": [
    {
      "to": 20,
      "from": 13,
      "name": "Pattern Hunter",
      "slug": "02-pattern-hunter",
      "bestFor": "Time-pressed audiences, building consensus, when data is strong",
      "matchId": "019dd95a-07fe-70ce-8d3e-27658cc21e8b",
      "evidence": "Series of analyze_data slides on GPT-4, o1, Claude 3.5, Llama 3, openness, contamination, leaderboards",
      "position": 2,
      "objective": "Show frontier model gap is closing through multiple data points",
      "structure": "Evidence A -> Evidence B -> Evidence C -> Pattern/Conclusion",
      "confidence": 78,
      "description": "Group multiple pieces of evidence that together point to a pattern or conclusion"
    }
  ],
  "imagePathAlt": null,
  "thumbSrc": null,
  "thumbSrcAlt": null,
  "locked": true
}